YJIT Benchmarks

Details for Benchmarks at 2022-12-03 20:10:05

Overall YJIT is 37.6% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 38.4% faster than CRuby!
The basic "faster" measurement is the geomean of all "headlining" x86 benchmarks on this page.

Headlining Benchmarks

These are "headlining" because the "overall" speedup above is based on these benchmarks specifically.

Speed of each Ruby implementation (iterations/second) relative to the CRuby interpreter. Higher is better.

Other Benchmarks

Speed of each Ruby implementation (iterations/second) relative to the CRuby interpreter. Higher is better.

MicroBenchmarks

Speed of each Ruby implementation (iterations/second) relative to the CRuby interpreter. Higher is better.

Want Raw Graphs and CSV?

Benchmarks Speed Details

Benchmark Memory Usage Details

Number of Iterations and Warmups Tested

bench No JIT warmups No JIT iters YJIT warmups YJIT iters
activerecord 5 191 5 191
hexapdf 5 15 5 15
liquid-render 5 154 5 154
mail 5 139 5 139
psych-load 5 15 5 15
railsbench 5 15 5 15
ruby-lsp 5 282 5 282
binarytrees 5 86 5 86
chunky_png 5 32 5 32
erubi 5 68 5 68
erubi_rails 5 1086 5 1086
etanni 5 42 5 42
fannkuchredux 5 20 5 20
lee 5 22 5 22
nbody 5 253 5 253
optcarrot 5 15 5 15
rubykon 5 15 5 15
30k_ifelse 5 49 5 49
30k_methods 5 20 5 20
cfunc_itself 5 496 5 496
fib 5 326 5 326
getivar 5 438 5 438
keyword_args 5 374 5 374
respond_to 5 694 5 694
setivar 5 378 5 378
str_concat 5 489 5 489

Different Ruby configurations want different amounts of warmup. With no JIT, CRuby needs hardly any. YJIT and MJIT 3.0 both warm up quite quickly, while MJIT in 3.1 often slows down for a time as it compiles, after an unpredictable delay.

Benchmark YJIT Stats

Hover your cursor over the benchmark names for descriptions of each benchmark.

bench Exit Report Inline Outlined Comp iSeqs Comp Blocks Inval Inval Ratio Bind Alloc Bind Set Const Bumps
activerecord (click) 2264155 2262733 25 370 6 1% 0 0 0
hexapdf (click) 1695349 1695067 819 10211 216 2% 0 0 0
liquid-render (click) 583779 582929 156 1846 33 1% 0 0 0
mail (click) 1243419 1241675 373 4662 176 3% 0 0 0
psych-load (click) 782807 781456 70 649 19 2% 0 0 0
railsbench (click) 5511338 5510576 1779 14242 482 3% 0 0 0
ruby-lsp (click) 5348930 5347871 6428 41507 1521 3% 14454 0 0
binarytrees (click) 131647 131305 16 139 4 2% 0 0 0
chunky_png (click) 803591 803220 89 1183 31 2% 0 0 0
erubi (click) 717167 715820 13 147 4 2% 0 0 0
erubi_rails (click) 4643348 4642632 329 2784 111 3% 0 0 0
etanni (click) 132439 132046 13 107 4 3% 0 0 0
fannkuchredux (click) 143849 142353 14 272 4 1% 0 0 0
lee (click) 792270 790601 79 812 25 3% 0 0 0
nbody (click) 137214 135367 15 244 6 2% 0 0 0
optcarrot (click) 555313 553472 203 4438 93 2% 0 0 0
rubykon (click) 271385 270969 146 1634 31 1% 0 0 0
30k_ifelse (click) 5280777 5280299 9268 57199 4 0% 0 0 0
30k_methods (click) 2021641 2019300 5787 19426 4 0% 0 0 0
cfunc_itself (click) 129581 127764 13 122 4 3% 0 0 0
fib (click) 128156 126611 13 111 4 3% 0 0 0
getivar (click) 129935 127975 13 138 4 2% 0 0 0
keyword_args (click) 130363 128211 14 124 4 3% 0 0 0
respond_to (click) 130085 128068 13 138 5 3% 0 0 0
setivar (click) 121749 119789 13 118 4 3% 0 0 0
str_concat (click) 122630 120291 15 137 6 4% 0 0 0

YJIT stats correspond to the YJIT stats exit report.

Note: currently, all stats are collected on x86_64, not ARM.

Raw JSON data files

All graphs and table data in this page comes from processing these data files, which come from benchmark runs.